harness-claude

Harness Engineering

Mechanical constraints for AI agents. Ship faster without the chaos.

Why This Exists

AI coding agents are powerful, but unreliable without structure. Left unconstrained, they introduce circular dependencies, violate architectural boundaries, and generate drift that compounds across a codebase. Teams respond with code review backlogs and manual checklists — trading agent speed for human bottlenecks.

Harness Engineering takes a different approach: mechanical enforcement, not hope.

Instead of relying on prompts and conventions, harness encodes your architectural decisions as machine-checkable constraints. Agents get real-time feedback when they violate boundaries. Entropy is detected and cleaned automatically. Every rule is validated on every change.

For tech leads and architects: Scale AI-assisted development across your team with confidence. Define constraints once, enforce them everywhere — across agents, developers, and CI.

For individual developers: Stop babysitting your AI agent. Give it guardrails and let it execute. Spend your time on design decisions, not cleanup.

Key Features

• Cross-Platform Support — Fully tested on Windows, macOS, and Linux with mechanical enforcement preventing platform-specific regressions
• Context Engineering — Repository-as-documentation keeps agents grounded in project reality, not stale training data
• Architectural Constraints — Layered dependency rules enforced by ESLint, not willpower
• Agent Feedback Loop — Self-correcting agents with peer review and real-time validation
• Entropy Management — Automated detection of dead code, doc drift, and structural decay
• Implementation Strategy — Depth-first execution: one feature to 100% before the next begins
• Key Performance Indicators — Measure agent autonomy, harness coverage, and context density
• Orchestrator Gateway API — Token-scoped bearer auth on a versioned /api/v1/* surface with append-only audit log, three bridge-primitive endpoints (jobs/maintenance, interactions/{id}/resolve, events SSE), HMAC SHA-256-signed webhook subscriptions (X-Harness-Signature: sha256=<hex>) with event-bus fan-out, and a vendored OpenAPI artifact at docs/api/openapi.yaml. External bridges (Slack, Discord, GitHub Apps) build against a published, versioned contract instead of coupling to internals. See ADR 0011. See examples/slack-echo-bridge/ for the canonical reference consumer — a standalone Node bridge that verifies HMAC signatures and posts to Slack on maintenance.completed.
• Granular Task Routing — Spec B extends agent.routing with per-skill and per-cognitive-mode axes, fallback chains, and a /routing dashboard panel + harness routing trace CLI for inspecting decisions. See the Per-skill and per-mode routing section.
• Session Search & Insights — SQLite FTS5 index over .harness/sessions/ and .harness/archive/sessions/ with BM25 ranking; LLM-generated retrospective llm-summary.md written on session archive; composite harness insights aggregator combining health, entropy, decay, attention, and impact. New CLI commands harness search "<query>" and harness insights, plus MCP tools search_sessions, summarize_session, insights_summary. See ADR 0013.
• Skill Proposals — Agents emit skill candidates (new or refinement) via the emit_skill_proposal MCP tool; proposals queue in .harness/proposals/ and route through a mechanical soundness gate before reviewer approval. Every skill carries provenance: community | agent-proposed | user-authored. CLI: harness proposals list|show|approve|reject. Dashboard review queue at /s/proposals. See ADR 0016.

Quick Start

Pick the install path that matches how you use harness: